Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    LaTeX math formulas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.64
     Efq
    -0.62
    Datuak
    -0.61
     يتيمه
    -0.58
     lenker
    -0.58
    oredCriteria
    -0.57
     myſelf
    -0.56
    Portale
    -0.56
    FormTagHelper
    -0.54
    μως
    -0.54
    POSITIVE LOGITS
    <bos>
    0.39
    dar
    0.38
    ho
    0.38
     [
    0.37
    end
    0.37
    dis
    0.37
    oh
    0.37
    b
    0.37
    usercontent
    0.36
    bin
    0.36
    Act Density 2.897%

    No Known Activations